@inproceedings{gao-etal-2026-bg,
title = "{BG}-{RAG}: Concept-Mediated Bipartite Graphs for Scalable {RAG}",
author = "Gao, Hang and
Ding, Yangmin and
Han, Shaobo and
Jiang, Zhuocheng",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 2: Short Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-short.58/",
pages = "917--922",
ISBN = "979-8-89176-440-8",
abstract = "Graph-structured retrieval-augmented generation (GraphRAG) has shown strong potential for improving multi-hop reasoning in large language models. However, existing approaches typically depend on dense entity{--}entity linking, which is computationally expensive, susceptible to hallucinated relations, and difficult to maintain under continual updates. We present Bipartite Graph Retrieval-Augmented Generation (BG-RAG), a lightweight bipartite framework that organizes knowledge into three layers, from chunks to entities to concepts, and replaces direct entity links with concept-mediated connections. This design enables more efficient graph construction, reduces reliance on hallucination-prone relation-edge prediction by avoiding explicit entity{--}entity relation extraction, and naturally supports incremental updates without global reconstruction. Experiments on HotpotQA, 2Wiki, and MuSiQue show that BG-RAG achieves competitive performance against RAG and GraphRAG baselines. Its concept-mediated structure also provides a lightweight alternative to dense entity{--}entity graph construction. These results suggest that BG-RAG is a lightweight alternative for retrieval-augmented generation, particularly when avoiding dense entity{--}entity linking is desirable."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gao-etal-2026-bg">
<titleInfo>
<title>BG-RAG: Concept-Mediated Bipartite Graphs for Scalable RAG</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hang</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yangmin</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaobo</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhuocheng</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-440-8</identifier>
</relatedItem>
<abstract>Graph-structured retrieval-augmented generation (GraphRAG) has shown strong potential for improving multi-hop reasoning in large language models. However, existing approaches typically depend on dense entity–entity linking, which is computationally expensive, susceptible to hallucinated relations, and difficult to maintain under continual updates. We present Bipartite Graph Retrieval-Augmented Generation (BG-RAG), a lightweight bipartite framework that organizes knowledge into three layers, from chunks to entities to concepts, and replaces direct entity links with concept-mediated connections. This design enables more efficient graph construction, reduces reliance on hallucination-prone relation-edge prediction by avoiding explicit entity–entity relation extraction, and naturally supports incremental updates without global reconstruction. Experiments on HotpotQA, 2Wiki, and MuSiQue show that BG-RAG achieves competitive performance against RAG and GraphRAG baselines. Its concept-mediated structure also provides a lightweight alternative to dense entity–entity graph construction. These results suggest that BG-RAG is a lightweight alternative for retrieval-augmented generation, particularly when avoiding dense entity–entity linking is desirable.</abstract>
<identifier type="citekey">gao-etal-2026-bg</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-short.58/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>917</start>
<end>922</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BG-RAG: Concept-Mediated Bipartite Graphs for Scalable RAG
%A Gao, Hang
%A Ding, Yangmin
%A Han, Shaobo
%A Jiang, Zhuocheng
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-440-8
%F gao-etal-2026-bg
%X Graph-structured retrieval-augmented generation (GraphRAG) has shown strong potential for improving multi-hop reasoning in large language models. However, existing approaches typically depend on dense entity–entity linking, which is computationally expensive, susceptible to hallucinated relations, and difficult to maintain under continual updates. We present Bipartite Graph Retrieval-Augmented Generation (BG-RAG), a lightweight bipartite framework that organizes knowledge into three layers, from chunks to entities to concepts, and replaces direct entity links with concept-mediated connections. This design enables more efficient graph construction, reduces reliance on hallucination-prone relation-edge prediction by avoiding explicit entity–entity relation extraction, and naturally supports incremental updates without global reconstruction. Experiments on HotpotQA, 2Wiki, and MuSiQue show that BG-RAG achieves competitive performance against RAG and GraphRAG baselines. Its concept-mediated structure also provides a lightweight alternative to dense entity–entity graph construction. These results suggest that BG-RAG is a lightweight alternative for retrieval-augmented generation, particularly when avoiding dense entity–entity linking is desirable.
%U https://aclanthology.org/2026.aacl-short.58/
%P 917-922
Markdown (Informal)
[BG-RAG: Concept-Mediated Bipartite Graphs for Scalable RAG](https://aclanthology.org/2026.aacl-short.58/) (Gao et al., AACL-IJCNLP 2026)
ACL
- Hang Gao, Yangmin Ding, Shaobo Han, and Zhuocheng Jiang. 2026. BG-RAG: Concept-Mediated Bipartite Graphs for Scalable RAG. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 2: Short Papers), pages 917–922, Hengqin, China. Association for Computational Linguistics.